Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    journal policies and archiving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reservation
    -0.09
     Ips
    -0.08
     ಬ್ರ
    -0.08
     Booking
    -0.07
     .↵
    -0.07
    <=
    -0.07
     resort
    -0.07
     bracket
    -0.07
    br
    -0.07
     <=
    -0.07
    POSITIVE LOGITS
    על
    0.10
    خاص
    0.08
    Congratulations
    0.08
    เด
    0.08
     nerve
    0.07
    戻
    0.07
     tass
    0.07
    udas
    0.07
    Authority
    0.07
     enzyme
    0.07
    Act Density 0.001%

    No Known Activations